Yalçin I., Karakaş G., Can R., Kocaman S., Saunier S., Albinet C.

UZALCBS 2022 Sempozyumu, Ankara, Turkey, 17 - 19 November 2022, no.12850, pp.1-6

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.15659/uzalcbs2022.12850
  • City: Ankara
  • Country: Turkey
  • Page Numbers: pp.1-6
  • Hacettepe University Affiliated: Yes


Various applications such as monitoring the changes on Earth’s surface caused by natural hazards, rapid urbanization, etc., disaster management, planning of urban areas and agricultural lands, monitoring of natural resources have increased the need for up-to-date land cover maps and these maps must be produced with high temporal and spatial resolution. The data collection method used in the production of these maps is determined by taking into account the parameters such as the size of the study area, time and cost. For this purpose, the use of optical and radar satellite images, remote sensing techniques and artificial intelligence algorithms appear with an increasing frequency in the literature. MAXAR Technologies, one of the very high resolution satellite data providers, has started to offer images in High Definition (HD) format obtained from 30 cm Ground Sampling Distance (GSD) using advanced image processing methods. In this study, it was aimed to produce land cover maps with a deep learning approach using HD images of a selected study area. The defined classes were water surface, vegetation, asphalt, building, shade and open areas. The results showed that HD images are useful in land cover map production studies in urban areas and high classification accuracy can be obtained from the deep learning methods.